HAR-stacked-residual-bidir-LSTMs
Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
AI summary
Activity recognizer
An implementation of a deep neural network architecture for Human Activity Recognition using stacked residual bidirectional LSTM cells with TensorFlow.
- stars
- 319
- forks
- 100
- watching
- 19
- awesome list
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Human Activity Detector
An LSTM-based human activity recognition system using smartphone sensor data.
Activity recognition
This project aims to recognize human activities using a smartphone's accelerometer and gyroscope data with an LSTM RNN.
NER model
Named Entity Recognition model using LSTM and CRF with character embeddings
Time series classifier
An implementation of a Long Short-term memory network for time-series classification using Python and TensorFlow
Face recognizer
An implementation of a deep face recognition algorithm in TensorFlow
Attention network
A Gluon implementation of Residual Attention Network for image classification tasks
Image classifier
Implementing a deep learning framework for image classification using Residual Attention Network architecture
ActivityNet solver
An implementation of the 2016 ActivityNet action recognition challenge using a CNN + LSTM approach with multi-threaded loading.
Language model
An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch for word language modeling
NER tool
Named-entity recognition using neural networks.
Location predictor
Recurrent neural network model for predicting people's next location based on spatial and temporal features
Character-aware NLP model
An implementation of Character-Aware Neural Language Models using TensorFlow and combining multiple neural network architectures.
Action Recognition Model
Replication of a PyTorch model for action recognition and detection from skeleton data
Deep network architecture
An implementation of Wide Residual Networks in PyTorch for efficient deep learning on CIFAR10/100 datasets.
Image Segmentation Network
Re-implementation of a 100-layer fully convolutional network architecture for image segmentation
Featured in 1 awesome list
Each link jumps to the spot where the list mentions HAR-stacked-residual-bidir-LSTMs.